CN103500073A - Method and device for data block migration - Google Patents
Method and device for data block migration Download PDFInfo
- Publication number
- CN103500073A CN103500073A CN201310464699.2A CN201310464699A CN103500073A CN 103500073 A CN103500073 A CN 103500073A CN 201310464699 A CN201310464699 A CN 201310464699A CN 103500073 A CN103500073 A CN 103500073A
- Authority
- CN
- China
- Prior art keywords
- migration
- data block
- queue
- ioq
- bandwidth
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Debugging And Monitoring (AREA)
Abstract
The invention discloses a method and device for data block migration. The method includes the steps that the maximum bandwidth which permits an I/O request of an upper-layer application on a bottom-layer hierarchical storage device is set, flow of the I/O request of the upper-layer application on the bottom-layer hierarchical storage device is monitored, remaining bandwidth of the bottom-layer hierarchical storage device is calculated, when a data block needs to be migrated, whether the remaining bandwidth of the bottom-layer hierarchical storage device exists is judged, and if yes, migration I/O operation of the data block is executed. According to the method and device, under the condition that intensive migration I/O operation occurs, sufficient bandwidth can be supplied for the migration I/O operation. The remaining bandwidth is used for executing the migration I/O operation of data blocks needing migration, batch data migration is achieved, real-time performance and migration efficiency of data migration are improved, meanwhile a user defined bandwidth is set, the minimum bandwidth is used as the migration bandwidth, and influence on normal I/O operation is reduced as much as possible.
Description
Technical field
The present invention relates to data processing field, be specifically related to a kind of data block moving method and device.
Background technology
In the hierarchical stor be directed to based on the piece DBMS, the data Autonomic Migration Framework that to ask without frequentation is to lower equipment in the carrying cost level, the storage space that discharges higher cost is given the data of more frequently access or higher priority, thereby greatly reduce the non-importance data space shared at the one-level local disk, accelerate the memory property of whole system, reduce the cost that has of whole storage system, and then obtain better cost performance.The classification storage of based on data piece is a kind of fine-grained data staging Managed Solution, the granularity refinement of data management can be arrived according to the defined extension blocks level of application demand, therefore more accurate for the management of data.When intensive I/O access bottom data occurring, will produce hot spot data, at this moment needed the upgrading migration operation of hot spot data, so that hot spot data can the better storage resources of usability, thereby improve the storage system overall performance.But, in the classification storage migration scheme of existing based on data piece, migration operation for hot spot data exists migration frequent, when the hot spot data piece occurring, move immediately, cause the hot spot data transport efficiency low, the problem of waste resource, affected the practical application effect that data staging is managed.
Summary of the invention
The technical issues that need to address of the present invention are to provide a kind of data block moving method and device, can improve real-time and the transport efficiency of Data Migration, guarantee the reliability of migration simultaneously.
In order to solve the problems of the technologies described above, the invention provides a kind of data block moving method, comprising:
Arrange and allow the maximum bandwidth of upper layer application to bottom hierarchical storage apparatus I/O I/O request;
Monitor the flow of described upper layer application to described bottom hierarchical storage apparatus I/O request, add up the remaining bandwidth of described bottom hierarchical storage apparatus;
When needs are moved data block, judge whether described bottom hierarchical storage apparatus exists remaining bandwidth, if exist, carry out the migration I/O operation of described data block.
Further, described method also comprises: user-defined remaining bandwidth is set;
After judging described bottom hierarchical storage apparatus and having remaining bandwidth, the described remaining bandwidth also statistics obtained and described user-defined remaining bandwidth compare, and therefrom select the bandwidth of less remaining bandwidth as the migration I/O operation of described data block.
Further, described method also comprises:
When needs are moved data block, all data block organisation of migration that need are generated as to a migration I/O queue, IOQ, described migration I/O queue, IOQ comprises: the I/O operation of the data block contents of migration and migration data piece.
Further, the migration I/O of the described data block of described execution operation comprises:
Described migration I/O queue, IOQ is joined and carries out in I/O queue, IOQ, when the setting-up time of the timer of described execution I/O queue, IOQ then after, the data block in described migration I/O queue, IOQ is carried out to migration I/O operation.
Further, described when needs are moved data block, all data block organisation of migration that need are generated as to a migration I/O queue, IOQ, comprising:
When reaching sometime migration during the cycle, scan the data block in described bottom hierarchical storage apparatus, add up the data characteristics information of described data block, verify that described data characteristics information obtains the hot spot data piece, the data block contents of this hot spot data piece and corresponding migration I/O operation are joined in described migration I/O queue, IOQ.
In order to solve the problems of the technologies described above, the present invention also provides a kind of data block moving apparatus, comprising:
The bandwidth control module, allow the maximum bandwidth of upper layer application to bottom hierarchical storage apparatus I/O I/O request for arranging;
The bandwidth monitor module, for monitoring the flow of described upper layer application to described bottom hierarchical storage apparatus I/O request, add up the remaining bandwidth of described bottom hierarchical storage apparatus;
Transferring module, for when needs are moved data block, judge whether described bottom hierarchical storage apparatus exists remaining bandwidth, if exist, carries out the migration I/O operation of described data block.
Further, described device also comprises: remaining bandwidth arranges module, for user-defined remaining bandwidth is set;
Described transferring module, also for after judging described bottom hierarchical storage apparatus and having remaining bandwidth, the described remaining bandwidth also statistics obtained and described user-defined remaining bandwidth compare, and therefrom select the bandwidth of less remaining bandwidth as the migration I/O operation of described data block.
Further, described transferring module, also, for when needs are moved data block, all data block organisation of migration that need are generated as to a migration I/O queue, IOQ, described migration I/O queue, IOQ comprises: the I/O operation of the data block contents of migration and migration data piece.
Further, described transferring module, for carrying out the migration I/O operation of described data block, comprising:
Described migration I/O queue, IOQ is joined and carries out in I/O queue, IOQ, when the setting-up time of the timer of described execution I/O queue, IOQ then after, the data block in described migration I/O queue, IOQ is carried out to migration I/O operation.
Further, described transferring module, for when needs are moved data block, be generated as a migration I/O queue, IOQ by all data block organisation of migration that need, and comprising:
When reaching sometime migration during the cycle, scan the data block in described bottom hierarchical storage apparatus, add up the data characteristics information of described data block, verify that described data characteristics information obtains the hot spot data piece, the data block contents of this hot spot data piece and corresponding migration I/O operation are joined in described migration I/O queue, IOQ.
Compared with prior art, data block moving method provided by the invention and device, the remaining bandwidth information that can use by obtaining the bottom hierarchical storage apparatus, guaranteeing has enough bandwidth to be moved the I/O operation in the situation that intensive I/O operation occurs; Safeguard the migration I/O queue, IOQ and carry out I/O queue, IOQ, utilize remaining bandwidth to carry out migration I/O operation to the data block of needs migration, realized the batch data migration, real-time and the transport efficiency of Data Migration have been improved, the User Defined bandwidth is set simultaneously, using minimum value as the migration bandwidth, and reduce is for the impact of normal I/O operation.
The accompanying drawing explanation
Fig. 1 is data block moving method process flow diagram in embodiment;
Fig. 2 is data block moving apparatus structural drawing in embodiment;
Fig. 3 safeguards the queue schematic diagram in embodiment;
Fig. 4 is data block migration system architecture figure in an application example;
Fig. 5 is the concrete operations process flow diagram that in an application example, transferring module is safeguarded the migration I/O queue, IOQ;
Fig. 6 is that in an application example, transferring module is carried out migration operation to the data block of needs migration, safeguards the migration I/O operational flowchart of carrying out I/O queue, IOQ.
Embodiment
For making the purpose, technical solutions and advantages of the present invention clearer, hereinafter in connection with accompanying drawing, embodiments of the invention are elaborated.It should be noted that, in the situation that do not conflict, the embodiment in the application and the feature in embodiment be combination in any mutually.
Embodiment:
As shown in Figure 1, the present embodiment provides a kind of data block moving method, comprises the following steps:
S101: arrange and allow the maximum bandwidth of upper layer application to bottom hierarchical storage apparatus I/O I/O request;
Maximum bandwidth is set to the bottom hierarchical storage apparatus can offer the maximum bandwidth that upper layer application is used, and the access ability that not the bottom hierarchical storage apparatus possesses self.While arranging, the access ability that the value of maximum bandwidth possesses than bottom hierarchical storage apparatus self is little.
S102: monitor the flow of upper layer application to bottom hierarchical storage apparatus I/O request, add up the remaining bandwidth of described bottom hierarchical storage apparatus;
Remaining bandwidth is that the maximum bandwidth arranged deducts the bandwidth that upper layer application access I/O request has been used.
S103: when needs are moved data block, judge whether described bottom hierarchical storage apparatus exists remaining bandwidth, if exist, carry out the migration I/O operation of described data block.
As a kind of optimal way, user-defined remaining bandwidth can also be set; In step S103, after judging described bottom hierarchical storage apparatus and having remaining bandwidth, also comprise: described remaining bandwidth and user-defined remaining bandwidth are compared, therefrom select the bandwidth of less remaining bandwidth as the data block migration.
While due to the data block to the needs migration, being moved the I/O operation, system also exists carries out normal I/O operational circumstances to the data block of bottom hierarchical storage apparatus, wherein, remaining bandwidth is for migration data, therefore, select the bandwidth of less remaining bandwidth as the data block migration, can guarantee at utmost to reduce the impact for normal I/O when improving transport efficiency.
Migration to data block comprises the upgrading migration to the hot spot data piece, with the degradation migration to cold data block, the hot spot data piece is the data block that access times are very high, the not accessed or access times of hot spot data tail off and just become cold data, from chronic device upgrade to accessing the equipment that performance is good, make the hot spot data can the better storage resources of usability, thereby improve the storage system overall performance, contrary, to cold data block degradation, migration refers to that the equipment transportation good from access performance is slow devices.
Migration I/O operation specifically refers to reads data block from current bottom memory device, and writes the bottom memory device of moving into.
In order to improve the efficiency of migration data, in this step, specifically comprise: when needs are moved data block, all data block organisation of migration that need are generated as to a migration I/O queue, IOQ, described migration I/O queue, IOQ comprises: the I/O operation of the data block contents of migration and migration data piece.Move queue by generation, when needs migration data piece, can batch type ground migration, thereby improved the transport efficiency of data.
As a kind of preferred mode, need in the present embodiment to safeguard two queues, as shown in Figure 3, one is the migration I/O queue, IOQ, one is to carry out I/O queue, IOQ, carry out I/O queue, IOQ and be to prepare the I/O request of access queue sent to lower floor's stage equipment, this queue for storing be to transmit from the generic block layer bio(block input output that gets off, the input and output of piece), namely carry out the normal I/O operation of read and write access operation I/O() and migration I/O operation.And the migration I/O queue, IOQ is in charge of I/O operation corresponding to data block that needs migration.
In step S103, in order to improve the efficiency of migration data, in this step, specifically comprise: when needs are moved data block, all data block organisation of migration that need are generated as to a migration I/O queue, IOQ, and described migration I/O queue, IOQ comprises: the I/O operation of the data block contents of migration and migration data piece.Move queue by generation, when needs migration data piece, can batch type ground migration, thereby improved the transport efficiency of data.
In step S103, carry out the migration I/O operation of described data block, comprising:
Described migration I/O queue, IOQ is joined and carries out in I/O queue, IOQ, when the setting-up time of the timer of described execution I/O queue, IOQ then after, the data block in described migration I/O queue, IOQ is carried out to migration I/O operation.
In the present embodiment, preferably, for described execution I/O queue, IOQ arranges a timer, can not carry out migration I/O operation after joining in the execution I/O queue, IOQ by described migration I/O queue, IOQ at once, but the setting-up time that waits timer then after, to described migration I/O queue, IOQ, corresponding data block is carried out migration I/O operation.
Take the hot spot data piece as example, when needs are moved data block, all data block organisation of migration that need be generated as to a migration I/O queue, IOQ, comprising:
When reaching sometime migration during the cycle, start to scan the data block in the bottom hierarchical storage apparatus, the data characteristics information of statistics piece, then verify that this data characteristics information obtains the hot spot data piece, the data block contents of this hot spot data piece and corresponding migration I/O operation are joined in described migration I/O queue, IOQ.
When intensive I/O access bottom data occurring, will produce hot spot data, at this moment needed the upgrading migration operation of hot spot data, so that hot spot data can the better storage resources of usability, thereby improve the storage system overall performance.But, at this moment in order to guarantee the consistance of data, can, to data processings that locked, at this moment trigger migration operation and can cause operating due to the locking mutual exclusion of data block can't be completed in time carrying out I/O when operation.If this hot spot data piece is locked, Data Migration can not occur, this hot spot data piece temporarily is retained in the migration I/O queue, IOQ, do not add the execution I/O queue, IOQ, add again the execution I/O queue, IOQ after release; When if this hot spot data piece is not locked, this hot spot data piece is normally moved to the I/O operation, join the execution I/O queue, IOQ, carry out migration I/O operation.
Because, be provided with in step S101 and allow the maximum bandwidth of upper layer application to bottom hierarchical storage apparatus I/O I/O request, preferably, in step S102, the monitoring upper layer application is during to the flow of bottom hierarchical storage apparatus I/O request, when upper layer application reaches maximum bandwidth to the flow of bottom hierarchical storage apparatus I/O request, will transmit the normal I/O operation of the bio(got off to general layer) blocked, join normal I/O queue, IOQ and carry out buffer memory; When the bottom hierarchical storage apparatus also has remaining bandwidth, normal I/O operation is joined to the execution I/O queue, IOQ, bio is converted to I/O request request and is handed down to the I/O operation that memory device carries out data.
As shown in Figure 2, the present embodiment provides a kind of data block moving apparatus, comprising:
The bandwidth control module, allow the maximum bandwidth of upper layer application to bottom hierarchical storage apparatus I/O I/O request for arranging;
The bandwidth monitor module, for monitoring the flow of described upper layer application to described bottom hierarchical storage apparatus I/O request, add up the remaining bandwidth of described bottom hierarchical storage apparatus;
Transferring module, for when needs are moved data block, judge whether described bottom hierarchical storage apparatus exists remaining bandwidth, if exist, carries out the migration I/O operation of described data block.
Described device also comprises: remaining bandwidth arranges module, for user-defined remaining bandwidth is set;
Described transferring module, also for after judging described bottom hierarchical storage apparatus and having remaining bandwidth, the described remaining bandwidth also statistics obtained and described user-defined remaining bandwidth compare, and therefrom select the bandwidth of less remaining bandwidth as the migration I/O operation of described data block.
Wherein, described transferring module, also for when needs are moved data block, be generated as a migration I/O queue, IOQ by all data block organisation of migration that need, and described migration I/O queue, IOQ comprises: the I/O operation of the data block contents of migration and migration data piece.
Described transferring module, for carrying out the migration I/O operation of described data block, comprising:
Described migration I/O queue, IOQ is joined and carries out in I/O queue, IOQ, when the setting-up time of the timer of described execution I/O queue, IOQ then after, the data block in described migration I/O queue, IOQ is carried out to migration I/O operation.
Described transferring module, for when needs are moved data block, be generated as a migration I/O queue, IOQ by all data block organisation of migration that need, and comprising:
When reaching sometime migration during the cycle, scan the data block in described bottom hierarchical storage apparatus, add up the data characteristics information of described data block, verify that described data characteristics information obtains the hot spot data piece, the data block contents of this hot spot data piece and corresponding migration I/O operation are joined in described migration I/O queue, IOQ.
In an application example, as shown in Figure 4, the I/O subsystem comprises: the data block moving apparatus in generic block layer, above-described embodiment and Block Device Driver layer, this I/O subsystem is positioned between file system layer (upper layer application) and layers of physical devices, and layers of physical devices comprises: IO bus, disc driver, hierarchical storage apparatus etc.The data block moving apparatus comprises: bandwidth control module, bandwidth monitor module, transferring module and user's configuration interface.
Need to safeguard two I/O administration queue in concrete enforcement, the queue relation as shown in Figure 3.At first be to safeguard and carry out I/O queue, IOQ by the bandwidth control module, carry out I/O queue, IOQ and be and prepare the I/O request of access queue sent to lower floor's stage equipment, this queue for storing be to transmit from the generic block layer bio got off to carry out read and write access operation I/O and migration operation I/O.Secondly, transferring module can be safeguarded a migration I/O queue, IOQ, and the I/O operation that the data block of needs migration is carried out is in charge of in this queue.In addition, the I/O subsystem has also been safeguarded a normal I/O queue, IOQ, for buffer memory, from the generic block layer, transmits the normal I/O operation of the bio(got off).
In the specific implementation, the I/O subsystem provides unified interface submit_bio, upper system is packaged just calls submit_bio and the operation of the execution read and write access in bio I/O is sent to the equipment of bottom after bio, submit_bio can call the generic_make_request interface function.The bandwidth control module will be utilized the generic_make_request function in specific implementation, call the bw_control_bio function and safeguard the normal I/O operating process of carrying out I/O queue, IOQ, comprise:
S201: call bw_control_bio function monitoring upper layer application the data of described bottom hierarchical storage apparatus are carried out to the bandwidth that read and write access operation I/O has been used;
S202: when having bio to be transferred to the I/O subsystem from the generic block layer, judge whether the bandwidth that upper layer application has been used reaches default maximum bandwidth, that is, whether the bandwidth that detects current distribution is finished, if reach, performs step S203; If do not reach perform step S204;
S203: general layer is transmitted to the normal I/O operation of the bio(got off) blocked, join normal I/O queue, IOQ and carry out buffer memory;
After some I/O migration operation is carried out, the bandwidth of bottom hierarchical storage apparatus that will release busy, now, just there will be remaining bandwidth, and temporary transient first buffer memory, when remaining bandwidth is arranged, then carry out migration operation.
S204: judge whether remaining bandwidth, if having, performed step S205, otherwise continued buffer memory,
S205: normal I/O operation is joined to the execution I/O queue, IOQ;
S206: carry out I/O queue, IOQ and safeguarded a timer, after the timer timing reaches, bio is converted to I/O request request and is handed down to the I/O operation that memory device carries out data.
In an application example, as shown in Figure 5, transferring module is safeguarded the migration I/O queue, IOQ, and concrete operations are as follows:
S301: transferring module, when reaching the scan period, starts the data block in the bottom hierarchical storage apparatus is carried out to the temperature scan operation characteristic information of statistics piece;
Specifically comprise: travel through all data blocks in whole hierarchical storage apparatus, to piece, list starts to travel through walk_blocklist; In traversal piece chained list, obtain block message, comprised the statistical value of quoting number of times of read/write in the middle of block message, after obtaining statistical value, the characteristic information access times M of computational data piece, access times represent cold and hot degree.
S302: more described characteristic information access times M and pre-set threshold value compare, and judge whether data block carries out upwards updating operation or degraded operation downwards, the extension blocks that mark need to move;
It is that hot spot data is carried out the upgrading migration that access times surpass the threshold value explanation, and being less than the threshold value explanation is cold data, carries out the degradation migration.
Wherein, the statistics etc. that also can quote number of times according to the access of the statistics of the access frequency of the digestion time of the digestion time of equipment, data block, data block, equipment judges whether data block carries out upwards updating operation or degraded operation downwards.
S303: will need data block contents and the corresponding migration I/O operation of the data block of migration to join in described migration I/O queue, IOQ.
As shown in Figure 6, provide transferring module to carry out migration operation to the data block of needs migration, called the bw_control_bio function and safeguard the migration I/O operating process of carrying out I/O queue, IOQ, specifically comprised the following steps:
S401: when needs are moved data block, transferring module is obtained the remaining bandwidth that the bandwidth monitor module is called the bottom hierarchical storage apparatus of bw_control_bio statistics;
S402: judge whether described bottom hierarchical storage apparatus exists remaining bandwidth, if exist, perform step S404; Otherwise, execution step S403;
Remaining bandwidth is that the maximum bandwidth arranged deducts the bandwidth that upper layer application access I/O request has been used.
S403: will move I/O and operate in buffer memory in the migration I/O queue, IOQ, and return to step S402, and judge whether described bottom hierarchical storage apparatus will exist remaining bandwidth;
S404: compare with user's predefine bandwidth, select the bandwidth of less bandwidth as migration operation;
S405: the migration I/O operation that will move in I/O queue, IOQ is sent to the execution I/O queue, IOQ;
S406: carry out I/O queue, IOQ and safeguarded a timer, the setting-up time of timer then after, the data block in described migration I/O queue, IOQ is carried out to migration I/O operation.
In order to guarantee the consistance of data, in step S301, transferring module is carried out the temperature scan operation to the data block in the bottom hierarchical storage apparatus, before traveling through all data blocks in whole hierarchical storage apparatus, can lock to metadata and blocks of data list, hot spot data locks and refers to that upper layer application accessing hot spot data, so the migration I/O of this hot spot data operation can not be carried out, although also joining of this migration I/O operation moved in I/O queue, IOQ, but can not be added into, carry out in I/O queue, IOQ, only have when upper layer application does not visit again this hot spot data piece, just the migration I/O of hot spot data piece operation just can join and carry out in I/O queue, IOQ, thereby carry out the migration I/O operation of this data block.
From above-described embodiment, can find out, with respect to prior art, the data block moving method and the device that in above-described embodiment, provide, by being set, upper layer application allows to use the maximum bandwidth of bottom stage equipment, obtain the remaining bandwidth information that the bottom hierarchical storage apparatus can be used, guaranteeing has enough bandwidth to be moved the I/O operation in the situation that intensive I/O operation occurs; Safeguard the migration I/O queue, IOQ and carry out I/O queue, IOQ, utilize remaining bandwidth to carry out migration I/O operation to the data block of needs migration, realized the batch data migration, real-time and the transport efficiency of Data Migration have been improved, the User Defined bandwidth is set simultaneously, using minimum value as the migration bandwidth, and reduce is for the impact of normal I/O operation.
One of ordinary skill in the art will appreciate that all or part of step in said method can come the instruction related hardware to complete by program, described program can be stored in computer-readable recording medium, as ROM (read-only memory), disk or CD etc.Alternatively, all or part of step of above-described embodiment also can realize with one or more integrated circuit.Correspondingly, each the module/unit in above-described embodiment can adopt the form of hardware to realize, also can adopt the form of software function module to realize.The present invention is not restricted to the combination of the hardware and software of any particular form.
The foregoing is only the preferred embodiments of the present invention, be not intended to limit protection scope of the present invention.According to summary of the invention of the present invention; also other various embodiments can be arranged; in the situation that do not deviate from spirit of the present invention and essence thereof; those of ordinary skill in the art are when making according to the present invention various corresponding changes and distortion; within the spirit and principles in the present invention all; any modification of doing, be equal to replacement, improvement etc., within protection scope of the present invention all should be included in.
Claims (10)
1. a data block moving method comprises:
Arrange and allow the maximum bandwidth of upper layer application to bottom hierarchical storage apparatus I/O I/O request;
Monitor the flow of described upper layer application to described bottom hierarchical storage apparatus I/O request, add up the remaining bandwidth of described bottom hierarchical storage apparatus;
When needs are moved data block, judge whether described bottom hierarchical storage apparatus exists remaining bandwidth, if exist, carry out the migration I/O operation of described data block.
2. the method for claim 1, it is characterized in that: described method also comprises: user-defined remaining bandwidth is set;
After judging described bottom hierarchical storage apparatus and having remaining bandwidth, the described remaining bandwidth also statistics obtained and described user-defined remaining bandwidth compare, and therefrom select the bandwidth of less remaining bandwidth as the migration I/O operation of described data block.
3. method as claimed in claim 2, it is characterized in that: described method also comprises:
When needs are moved data block, all data block organisation of migration that need are generated as to a migration I/O queue, IOQ, described migration I/O queue, IOQ comprises: the I/O operation of the data block contents of migration and migration data piece.
4. method as claimed in claim 3 is characterized in that:
The migration I/O operation of the described data block of described execution comprises:
Described migration I/O queue, IOQ is joined and carries out in I/O queue, IOQ, when the setting-up time of the timer of described execution I/O queue, IOQ then after, the data block in described migration I/O queue, IOQ is carried out to migration I/O operation.
5. method as claimed in claim 3 is characterized in that:
Described when needs are moved data block, all data block organisation of migration that need are generated as to a migration I/O queue, IOQ, comprising:
When reaching sometime migration during the cycle, scan the data block in described bottom hierarchical storage apparatus, add up the data characteristics information of described data block, verify that described data characteristics information obtains the hot spot data piece, the data block contents of this hot spot data piece and corresponding migration I/O operation are joined in described migration I/O queue, IOQ.
6. a data block moving apparatus comprises:
The bandwidth control module, allow the maximum bandwidth of upper layer application to bottom hierarchical storage apparatus I/O I/O request for arranging;
The bandwidth monitor module, for monitoring the flow of described upper layer application to described bottom hierarchical storage apparatus I/O request, add up the remaining bandwidth of described bottom hierarchical storage apparatus;
Transferring module, for when needs are moved data block, judge whether described bottom hierarchical storage apparatus exists remaining bandwidth, if exist, carries out the migration I/O operation of described data block.
7. device as claimed in claim 6, it is characterized in that: described device also comprises: remaining bandwidth arranges module, for user-defined remaining bandwidth is set;
Described transferring module, also for after judging described bottom hierarchical storage apparatus and having remaining bandwidth, the described remaining bandwidth also statistics obtained and described user-defined remaining bandwidth compare, and therefrom select the bandwidth of less remaining bandwidth as the migration I/O operation of described data block.
8. device as claimed in claim 7 is characterized in that:
Described transferring module, also for when needs are moved data block, be generated as a migration I/O queue, IOQ by all data block organisation of migration that need, and described migration I/O queue, IOQ comprises: the I/O operation of the data block contents of migration and migration data piece.
9. device as claimed in claim 8 is characterized in that:
Described transferring module, for carrying out the migration I/O operation of described data block, comprising:
Described migration I/O queue, IOQ is joined and carries out in I/O queue, IOQ, when the setting-up time of the timer of described execution I/O queue, IOQ then after, the data block in described migration I/O queue, IOQ is carried out to migration I/O operation.
10. device as claimed in claim 8 is characterized in that:
Described transferring module, for when needs are moved data block, be generated as a migration I/O queue, IOQ by all data block organisation of migration that need, and comprising:
When reaching sometime migration during the cycle, scan the data block in described bottom hierarchical storage apparatus, add up the data characteristics information of described data block, verify that described data characteristics information obtains the hot spot data piece, the data block contents of this hot spot data piece and corresponding migration I/O operation are joined in described migration I/O queue, IOQ.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310464699.2A CN103500073B (en) | 2013-10-08 | 2013-10-08 | A kind of data block moving method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310464699.2A CN103500073B (en) | 2013-10-08 | 2013-10-08 | A kind of data block moving method and device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN103500073A true CN103500073A (en) | 2014-01-08 |
CN103500073B CN103500073B (en) | 2016-05-18 |
Family
ID=49865289
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201310464699.2A Active CN103500073B (en) | 2013-10-08 | 2013-10-08 | A kind of data block moving method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103500073B (en) |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104461389A (en) * | 2014-12-03 | 2015-03-25 | 上海新储集成电路有限公司 | Automatically learning method for data migration in mixing memory |
CN105022753A (en) * | 2014-04-29 | 2015-11-04 | ***通信集团内蒙古有限公司 | Data storage method and system |
CN106537323A (en) * | 2014-07-31 | 2017-03-22 | 微软技术许可有限责任公司 | Storage device access mediation |
CN107092443A (en) * | 2017-04-28 | 2017-08-25 | 杭州宏杉科技股份有限公司 | Data migration method and device |
CN107832189A (en) * | 2017-10-31 | 2018-03-23 | 维沃移动通信有限公司 | A kind of monitoring method and mobile terminal of I/O systems |
CN109325016A (en) * | 2018-09-12 | 2019-02-12 | 杭州朗和科技有限公司 | Data migration method, device, medium and electronic equipment |
CN109343793A (en) * | 2018-09-11 | 2019-02-15 | 阿里巴巴集团控股有限公司 | Data migration method and device |
CN109460188A (en) * | 2018-11-13 | 2019-03-12 | 郑州云海信息技术有限公司 | A kind of data migration method, system, equipment and computer readable storage medium |
CN109844714A (en) * | 2016-10-28 | 2019-06-04 | 华睿泰科技有限责任公司 | System and method for distributing input/output band width within the storage system |
CN111142788A (en) * | 2019-11-29 | 2020-05-12 | 浪潮电子信息产业股份有限公司 | Data migration method and device and computer readable storage medium |
CN115756336A (en) * | 2022-12-02 | 2023-03-07 | 邵健康 | Data migration processing method and system based on storage service system and cloud platform |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101079902A (en) * | 2007-06-29 | 2007-11-28 | 清华大学 | A great magnitude of data hierarchical storage method |
CN102279714A (en) * | 2011-08-26 | 2011-12-14 | 上海文广科技(集团)有限公司 | Method and device for controlling input/output (IO) requests |
CN103106152A (en) * | 2012-12-13 | 2013-05-15 | 深圳先进技术研究院 | Data scheduling method based on gradation storage medium |
-
2013
- 2013-10-08 CN CN201310464699.2A patent/CN103500073B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101079902A (en) * | 2007-06-29 | 2007-11-28 | 清华大学 | A great magnitude of data hierarchical storage method |
CN102279714A (en) * | 2011-08-26 | 2011-12-14 | 上海文广科技(集团)有限公司 | Method and device for controlling input/output (IO) requests |
CN103106152A (en) * | 2012-12-13 | 2013-05-15 | 深圳先进技术研究院 | Data scheduling method based on gradation storage medium |
Cited By (21)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105022753A (en) * | 2014-04-29 | 2015-11-04 | ***通信集团内蒙古有限公司 | Data storage method and system |
CN105022753B (en) * | 2014-04-29 | 2018-09-04 | ***通信集团内蒙古有限公司 | A kind of date storage method and system |
CN106537323B (en) * | 2014-07-31 | 2019-09-17 | 微软技术许可有限责任公司 | Storage device access is reconciled |
CN106537323A (en) * | 2014-07-31 | 2017-03-22 | 微软技术许可有限责任公司 | Storage device access mediation |
US10686721B2 (en) | 2014-07-31 | 2020-06-16 | Microsoft Technology Licensing, Llc | Storage device access mediation |
CN104461389B (en) * | 2014-12-03 | 2017-10-13 | 上海新储集成电路有限公司 | A kind of method of the self study of Data Migration in mixing memory |
CN104461389A (en) * | 2014-12-03 | 2015-03-25 | 上海新储集成电路有限公司 | Automatically learning method for data migration in mixing memory |
CN109844714B (en) * | 2016-10-28 | 2022-08-09 | 华睿泰科技有限责任公司 | System and method for allocating input/output bandwidth in a storage system |
CN109844714A (en) * | 2016-10-28 | 2019-06-04 | 华睿泰科技有限责任公司 | System and method for distributing input/output band width within the storage system |
CN107092443A (en) * | 2017-04-28 | 2017-08-25 | 杭州宏杉科技股份有限公司 | Data migration method and device |
CN107092443B (en) * | 2017-04-28 | 2020-04-07 | 杭州宏杉科技股份有限公司 | Data migration method and device |
CN107832189A (en) * | 2017-10-31 | 2018-03-23 | 维沃移动通信有限公司 | A kind of monitoring method and mobile terminal of I/O systems |
CN107832189B (en) * | 2017-10-31 | 2020-09-01 | 维沃移动通信有限公司 | Monitoring method of I/O system and mobile terminal |
CN109343793A (en) * | 2018-09-11 | 2019-02-15 | 阿里巴巴集团控股有限公司 | Data migration method and device |
CN109343793B (en) * | 2018-09-11 | 2021-09-07 | 创新先进技术有限公司 | Data migration method and device |
CN109325016A (en) * | 2018-09-12 | 2019-02-12 | 杭州朗和科技有限公司 | Data migration method, device, medium and electronic equipment |
CN109460188A (en) * | 2018-11-13 | 2019-03-12 | 郑州云海信息技术有限公司 | A kind of data migration method, system, equipment and computer readable storage medium |
CN111142788A (en) * | 2019-11-29 | 2020-05-12 | 浪潮电子信息产业股份有限公司 | Data migration method and device and computer readable storage medium |
CN111142788B (en) * | 2019-11-29 | 2021-10-15 | 浪潮电子信息产业股份有限公司 | Data migration method and device and computer readable storage medium |
CN115756336A (en) * | 2022-12-02 | 2023-03-07 | 邵健康 | Data migration processing method and system based on storage service system and cloud platform |
CN115756336B (en) * | 2022-12-02 | 2023-09-15 | 深圳市大道四九科技有限公司 | Data migration processing method and system based on storage service system and cloud platform |
Also Published As
Publication number | Publication date |
---|---|
CN103500073B (en) | 2016-05-18 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103500073A (en) | Method and device for data block migration | |
CN108616382B (en) | Method and device for upgrading network card firmware, network card and equipment | |
US11907561B2 (en) | Data backup method and apparatus | |
CN103473142B (en) | Virtual machine migration method under a kind of cloud computing operating system and device | |
CN102223394A (en) | Remote direct storage access | |
US10678437B2 (en) | Method and device for managing input/output (I/O) of storage device | |
CN110096220B (en) | Distributed storage system, data processing method and storage node | |
US10642822B2 (en) | Resource coordination method, apparatus, and system for database cluster | |
CN106648896B (en) | Method for dual-core sharing of output peripheral by Zynq chip under heterogeneous-name multiprocessing mode | |
US8380936B2 (en) | Multi-core processor system and multi-core processor | |
WO2018049873A1 (en) | Application scheduling method and device | |
CN110727403B (en) | Metadata management method and device | |
CN108141471B (en) | Method, device and equipment for compressing data | |
US20170054803A1 (en) | Information processing device, method, and system | |
KR101097777B1 (en) | A method, system and computer readable media for managing hybrid memory | |
CN103618762A (en) | System and method for enterprise service bus state pretreatment based on AOP | |
US20180089092A1 (en) | Method and device for managing caches | |
CN114168490A (en) | Method for determining memory recovery threshold and related equipment | |
CN114356215A (en) | Distributed cluster and control method of distributed cluster lock | |
CN104281587A (en) | Connection establishing method and device | |
CN110795202A (en) | Resource allocation method and device of virtualized cluster resource management system | |
CN104349506A (en) | Association management method, wireless access device and system | |
CN112468317A (en) | Cluster topology updating method, system, equipment and computer storage medium | |
CN110865901B (en) | Method and device for building EC (embedded control) strip | |
CN111737013B (en) | Chip resource management method and device, storage medium and system chip |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant |